@article{knowledgeboostingduringlowlatency, title = {Knowledge boosting during low-latency inference}, author = {Vidya Srinivas and Malek Itani and Tuochao Chen and Sefik Emre Eskimez and Takuya Yoshioka and Shyamnath Gollakota}, year = {2024}, eprint = {2407.11055}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.11055v3}, }